Aesthetic Assessment of Chinese Handwritings Based on Vision Language Models

• URL: http://arxiv.org/abs/2603.26768v1
• Date: Tue, 24 Mar 2026 07:57:26 GMT
• Title: Aesthetic Assessment of Chinese Handwritings Based on Vision Language Models
• Abstract summary: We leverage vision-language models (VLMs) to analyze the quality of handwritten Chinese characters and generate multi-level feedback.<n>We explore both low-rank adaptation (LoRA)-based fine-tuning strategies and in-context learning methods to integrate aesthetic assessment knowledge into VLMs.
• Score: 14.72561407532963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The handwriting of Chinese characters is a fundamental aspect of learning the Chinese language. Previous automated assessment methods often framed scoring as a regression problem. However, this score-only feedback lacks actionable guidance, which limits its effectiveness in helping learners improve their handwriting skills. In this paper, we leverage vision-language models (VLMs) to analyze the quality of handwritten Chinese characters and generate multi-level feedback. Specifically, we investigate two feedback generation tasks: simple grade feedback (Task 1) and enriched, descriptive feedback (Task 2). We explore both low-rank adaptation (LoRA)-based fine-tuning strategies and in-context learning methods to integrate aesthetic assessment knowledge into VLMs. Experimental results show that our approach achieves state-of-the-art performances across multiple evaluation tracks in the CCL 2025 workshop on evaluation of handwritten Chinese character quality.

Related papers

• Chinese Essay Rhetoric Recognition Using LoRA, In-context Learning and Model Ensemble [5.633877879389439]
  Rhetoric recognition is a critical component in automated essay scoring.<n>We leverage Large Language Models (LLMs) for the Chinese rhetoric recognition task.<n>Our method achieves the best performance on all three tracks of CCL 2025 Chinese essay rhetoric recognition evaluation task.
  arXiv  Detail & Related papers  (2026-03-24T07:58:05Z)
• Exposía: Academic Writing Assessment of Exposés and Peer Feedback [56.428320613219306]
  We present Exposa, the first public dataset that connects writing and feedback assessment in higher education.<n>We use Exposa to benchmark state-of-the-art open-source large language models (LLMs) for two tasks: automated scoring of (1) the proposals and (2) the student reviews.
  arXiv  Detail & Related papers  (2026-01-10T11:33:26Z)
• CDTP: A Large-Scale Chinese Data-Text Pair Dataset for Comprehensive Evaluation of Chinese LLMs [71.01843542502438]
  We present a comprehensive benchmark for evaluating Chinese Large Language Models (CB-ECLLM)<n>CB-ECLLM is based on the newly constructed Chinese Data-Text Pair (CDTP) dataset.<n>CDTP comprises over 7 million aligned text pairs, each consisting of unstructured text coupled with one or more corresponding triples, alongside a total of 15 million triples spanning four critical domains.
  arXiv  Detail & Related papers  (2025-10-07T15:33:52Z)
• Help Me Write a Story: Evaluating LLMs' Ability to Generate Writing Feedback [57.200668979963694]
  We present a novel test set of 1,300 stories that we corrupted to intentionally introduce writing issues.<n>We study the performance of commonly used LLMs in this task with both automatic and human evaluation metrics.
  arXiv  Detail & Related papers  (2025-07-21T18:56:50Z)
• Fùxì: A Benchmark for Evaluating Language Models on Ancient Chinese Text Understanding and Generation [20.87296508045343]
  We introduce Fuxi, a comprehensive benchmark that evaluates both understanding and generation capabilities across 21 diverse tasks.<n>We reveal significant performance gaps between understanding and generation tasks, with models achieving promising results in comprehension but struggling considerably in generation tasks.<n>Our findings highlight the current limitations in ancient Chinese text processing and provide insights for future model development.
  arXiv  Detail & Related papers  (2025-03-20T04:26:40Z)
• VisTW: Benchmarking Vision-Language Models for Traditional Chinese in Taiwan [20.92636353621876]
  This paper proposes a comprehensive evaluation benchmark for Visual Language Models (VLM) in Traditional Chinese.<n>Our evaluation suite, the first of its kind, contains two complementary components: VisTW-MCQ and VisTW-Dialogue.
  arXiv  Detail & Related papers  (2025-03-13T14:49:35Z)
• UKTA: Unified Korean Text Analyzer [7.342330109393445]
  UKTA (Unified Korean Text Analyzer) is a comprehensive Korea text analysis and writing evaluation system.<n>UKTA provides accurate low-level morpheme analysis, key lexical features for mid-level explainability, and transparent high-level rubric-based writing scores.
  arXiv  Detail & Related papers  (2025-02-11T13:30:56Z)
• Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education [1.6340559025561785]
  Large language model (LLM)-based evaluation pipelines have demonstrated their capability to robustly evaluate machine-generated text. We investigate whether LLMs can effectively assess human-written text for educational purposes.
  arXiv  Detail & Related papers  (2024-07-24T06:02:57Z)
• CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation [49.41531871253317]
  We present a new Chinese Vision- Language Understanding Evaluation benchmark dataset. The selection of object categories and images is entirely driven by Chinese native speakers. We find that fine-tuning on Chinese culture-related VL datasets effectively enhances VLMs' understanding of Chinese culture.
  arXiv  Detail & Related papers  (2024-07-01T08:35:37Z)
• Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning [61.34060587461462]
  We propose a two-stage framework for Chinese Text Recognition (CTR) We pre-train a CLIP-like model through aligning printed character images and Ideographic Description Sequences (IDS) This pre-training stage simulates humans recognizing Chinese characters and obtains the canonical representation of each character. The learned representations are employed to supervise the CTR model, such that traditional single-character recognition can be improved to text-line recognition.
  arXiv  Detail & Related papers  (2023-09-03T05:33:16Z)
• OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models [122.27878464009181]
  We conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available.
  arXiv  Detail & Related papers  (2023-05-13T11:28:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.